Related papers: Mathematical Analysis of Adversarial Attacks

Adversarial reprogramming, introduced by Elsayed, Goodfellow, and Sohl-Dickstein, seeks to repurpose a neural network to perform a different task, by manipulating its input without modifying its weights. We prove that two-layer ReLU neural…

Learned image compression (LIC) is becoming more and more popular these years with its high efficiency and outstanding compression quality. Still, the practicality against modified inputs added with specific noise could not be ignored.…

With the development of artificial intelligence technology, Federated Learning (FL) model has been widely used in many industries for its high efficiency and confidentiality. Some researchers have explored its confidentiality and designed…

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and…

The non-convexity of the artificial neural network (ANN) training landscape brings inherent optimization difficulties. While the traditional back-propagation stochastic gradient descent (SGD) algorithm and its variants are effective in…

Federated learning (FL) empowers privacypreservation in model training by only exposing users' model gradients. Yet, FL users are susceptible to gradient inversion attacks (GIAs) which can reconstruct ground-truth training data such as…

We examine one-hidden-layer neural networks with random weights. It is well-known that in the limit of infinitely many neurons they simplify to Gaussian processes. For networks with a polynomial activation, we demonstrate that the rate of…

Deep Reinforcement Learning (RL) powered by neural net approximation of the Q function has had enormous empirical success. While the theory of RL has traditionally focused on linear function approximation (or eluder dimension) approaches,…

RL-based medical questionnaire systems have shown great potential in medical scenarios. However, their safety and robustness remain unresolved. This study performs a comprehensive evaluation on adversarial attack methods to identify and…

We propose a novel low-rank initialization framework for training low-rank deep neural networks -- networks where the weight parameters are re-parameterized by products of two low-rank matrices. The most successful prior existing approach,…

Full Waveform Inversion (FWI) is a technique employed to attain a high resolution subsurface velocity model. However, FWI results are effected by the limited illumination of the model domain and the quality of that illumination, which is…

We analyze the performance of feedforward vs. recurrent neural network (RNN) architectures and associated training methods for learned frame prediction. To this effect, we trained a residual fully convolutional neural network (FCNN), a…

Reactive injection attacks are a class of security threats in wireless networks wherein adversaries opportunistically inject spoofing packets in the frequency band of a client thereby forcing the base-station to deploy…

Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tuning, or require many iterations to solve an optimization…

This paper proposes a Fast Graph Convolutional Neural Network (FGRNN) architecture to predict sequences with an underlying graph structure. The proposed architecture addresses the limitations of the standard recurrent neural network (RNN),…

Deep learning-based video manipulation methods have become widely accessible to the masses. With little to no effort, people can quickly learn how to generate deepfake (DF) videos. While deep learning-based detection methods have been…

Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerous misclassifications. We propose a novel way to interpret…

In recent years, deep neural networks have demonstrated outstanding performance in many machine learning tasks. However, researchers have discovered that these state-of-the-art models are vulnerable to adversarial examples: legitimate…

Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial…

In this paper, we explore theoretical properties of training a two-layered ReLU network $g(\mathbf{x}; \mathbf{w}) = \sum_{j=1}^K \sigma(\mathbf{w}_j^T\mathbf{x})$ with centered $d$-dimensional spherical Gaussian input $\mathbf{x}$…